Course info

Digital Teaching
The live lectures will be recorded and made available via Moodle afterwards.

Course Contents
- Basic inference and learning methods in computer vision
- Foundations of deep neural networks in computer vision
- Foundations of Bayesian networks and Markov random fields
- Computer vision as (probabilistic) inference
- Loss functions and robust estimation/modeling
- Image restoration
- Stereo
- Optical flow
- Object detection
- Tracking of (articulated) objects
- Semantic segmentation
- Current research topics

Literature
Literature recommendations will be updated regularly, an example might be:
- R. Szeliski, "Computer Vision: Algorithms and Applications", 2nd edition, Springer, 2022, [url=https://szeliski.org/Book/]website[/url]
- S. Prince, "Unterstanding Deep Learning", MIT Press, 2023, [url=https://udlbook.github.io/udlbook/]website[/url]
- S. Prince, "Computer Vision: Models, Learning, and Inference", Cambridge University Press, 2012, [url=http://www.computervisionmodels.com]website[/url]

Preconditions
Previous participation in the lectures Visual Computing and Computer Vision I is recommended.

Additional Information
[url]https://moodle.tu-darmstadt.de/course/view.php?id=29663[/url]

Online Offerings
Moodle